Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .google
    -0.07
    Mir
    -0.07
     surprising
    -0.07
    entrant
    -0.07
    unchecked
    -0.06
    企业
    -0.06
    ิเคราะห
    -0.06
     luk
    -0.06
     clumsy
    -0.06
    counts
    -0.06
    POSITIVE LOGITS
     redevelopment
    0.06
     بوده
    0.06
     trí
    0.06
     Goal
    0.06
     marathon
    0.06
    %m
    0.06
     Changes
    0.05
     modific
    0.05
    'T
    0.05
    aw
    0.05
    Act Density 0.090%

    No Known Activations